Robotic Waste Sorter With Agile Manipulation and Quickly Trainable Detector
Owing to human labor shortages, the automation of labor-intensive manual waste-sorting is needed. The goal of automating waste-sorting is to replace the human role of robust detection and agile manipulation of waste items with robots. To achieve this, we propose three methods. First, we provide a co...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9530533/ |
| _version_ | 1818641585937580032 |
|---|---|
| author | Takuya Kiyokawa Hiroki Katayama Yuya Tatsuta Jun Takamatsu Tsukasa Ogasawara |
| author_facet | Takuya Kiyokawa Hiroki Katayama Yuya Tatsuta Jun Takamatsu Tsukasa Ogasawara |
| author_sort | Takuya Kiyokawa |
| collection | DOAJ |
| description | Owing to human labor shortages, the automation of labor-intensive manual waste-sorting is needed. The goal of automating waste-sorting is to replace the human role of robust detection and agile manipulation of waste items with robots. To achieve this, we propose three methods. First, we provide a combined manipulation method using graspless push-and-drop and pick-and-release manipulation. Second, we provide a robotic system that can automatically collect object images to quickly train a deep neural–network model. Third, we provide a method to mitigate the differences in the appearance of target objects from two scenes: one for dataset collection and the other for waste sorting in a recycling factory. If differences exist, the performance of a trained waste detector may decrease. We address differences in illumination and background by applying object scaling, histogram matching with histogram equalization, and background synthesis to the source target-object images. Via experiments in an indoor experimental workplace for waste-sorting, we confirm that the proposed methods enable quick collection of the training image sets for three classes of waste items (<italic>i.e.,</italic> aluminum can, glass bottle, and plastic bottle) and detection with higher performance than the methods that do not consider the differences. We also confirm that the proposed method enables the robot quickly manipulate the objects. |
| first_indexed | 2024-12-16T23:29:31Z |
| format | Article |
| id | doaj.art-90ad80b6820c44ebbdcba2033f2863b0 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-16T23:29:31Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-90ad80b6820c44ebbdcba2033f2863b02022-12-21T22:11:55ZengIEEEIEEE Access2169-35362021-01-01912461612463110.1109/ACCESS.2021.31107959530533Robotic Waste Sorter With Agile Manipulation and Quickly Trainable DetectorTakuya Kiyokawa0https://orcid.org/0000-0002-8555-8489Hiroki Katayama1Yuya Tatsuta2Jun Takamatsu3https://orcid.org/0000-0001-7457-2878Tsukasa Ogasawara4https://orcid.org/0000-0001-9767-6039Nara Institute of Science and Technology (NAIST), Ikoma, Nara, JapanNara Institute of Science and Technology (NAIST), Ikoma, Nara, JapanNara Institute of Science and Technology (NAIST), Ikoma, Nara, JapanNara Institute of Science and Technology (NAIST), Ikoma, Nara, JapanNara Institute of Science and Technology (NAIST), Ikoma, Nara, JapanOwing to human labor shortages, the automation of labor-intensive manual waste-sorting is needed. The goal of automating waste-sorting is to replace the human role of robust detection and agile manipulation of waste items with robots. To achieve this, we propose three methods. First, we provide a combined manipulation method using graspless push-and-drop and pick-and-release manipulation. Second, we provide a robotic system that can automatically collect object images to quickly train a deep neural–network model. Third, we provide a method to mitigate the differences in the appearance of target objects from two scenes: one for dataset collection and the other for waste sorting in a recycling factory. If differences exist, the performance of a trained waste detector may decrease. We address differences in illumination and background by applying object scaling, histogram matching with histogram equalization, and background synthesis to the source target-object images. Via experiments in an indoor experimental workplace for waste-sorting, we confirm that the proposed methods enable quick collection of the training image sets for three classes of waste items (<italic>i.e.,</italic> aluminum can, glass bottle, and plastic bottle) and detection with higher performance than the methods that do not consider the differences. We also confirm that the proposed method enables the robot quickly manipulate the objects.https://ieeexplore.ieee.org/document/9530533/Robotics and automationrobot vision systemscomputer visionrecyclingmachine learningobject detection |
| spellingShingle | Takuya Kiyokawa Hiroki Katayama Yuya Tatsuta Jun Takamatsu Tsukasa Ogasawara Robotic Waste Sorter With Agile Manipulation and Quickly Trainable Detector IEEE Access Robotics and automation robot vision systems computer vision recycling machine learning object detection |
| title | Robotic Waste Sorter With Agile Manipulation and Quickly Trainable Detector |
| title_full | Robotic Waste Sorter With Agile Manipulation and Quickly Trainable Detector |
| title_fullStr | Robotic Waste Sorter With Agile Manipulation and Quickly Trainable Detector |
| title_full_unstemmed | Robotic Waste Sorter With Agile Manipulation and Quickly Trainable Detector |
| title_short | Robotic Waste Sorter With Agile Manipulation and Quickly Trainable Detector |
| title_sort | robotic waste sorter with agile manipulation and quickly trainable detector |
| topic | Robotics and automation robot vision systems computer vision recycling machine learning object detection |
| url | https://ieeexplore.ieee.org/document/9530533/ |
| work_keys_str_mv | AT takuyakiyokawa roboticwastesorterwithagilemanipulationandquicklytrainabledetector AT hirokikatayama roboticwastesorterwithagilemanipulationandquicklytrainabledetector AT yuyatatsuta roboticwastesorterwithagilemanipulationandquicklytrainabledetector AT juntakamatsu roboticwastesorterwithagilemanipulationandquicklytrainabledetector AT tsukasaogasawara roboticwastesorterwithagilemanipulationandquicklytrainabledetector |